Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms and numerical data in discussions or analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alker
    -0.17
    ples
    -0.15
    atern
    -0.15
    eprom
    -0.14
     chod
    -0.14
    ullet
    -0.14
    -spin
    -0.14
    arness
    -0.14
    comed
    -0.14
    092
    -0.14
    POSITIVE LOGITS
    Ø´ÙĪ
    0.14
    leme
    0.14
     presum
    0.14
    mine
    0.14
    ratings
    0.14
    MATRIX
    0.14
    Mappings
    0.14
     DOS
    0.14
    WebpackPlugin
    0.14
     impro
    0.13
    Act Density 0.018%

    No Known Activations